Mining Dynamics of Research Topics Based on the Combined LDA and WordNet

Li, Chao; Feng, Sen; Zeng, Qingtian; Ni, Weijian; Zhao, Hua; Duan, Hua

doi:10.1109/access.2018.2887314

Cited by 18 publications

(12 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This creates a communication barrier between business executives and modeling analysts [10]- [12]. In order to provide people of different roles with the information they need about the process [13], [14], the importance of maintaining text-based process descriptions alongside model-based ones has been recognized [15], [16].…”

Section: Process Models Have Beenmentioning

confidence: 99%

Missing Procedural Texts Repairing Based on Process Model and Activity Description Templates

Zeng

Tang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Textual descriptions of business process models are used as guidance for business executives. While it makes process models much easier to understand, missing procedural text is an important practical problem. In this paper, we propose a method of repairing missing procedural text based on business process model and text alignment. The proposed method realizes the process of repairing unstructured procedural texts based on structured models. Firstly, the key concepts of alignment and repair are formally defined. Then, text repair is divided into three subtasks: alignment creation, selecting the template for activities and procedural text repairing. Each subtasks are solved in a detailed way. Experiments with Chinese recipe documents demonstrate that the proposed method is capable of repairing the missing activities of procedural text. Furthermore, the proposed method could be easily adapted to other real-world domains as it is independent on complicated manually-designed rules. INDEX TERMS Procedural text, business process model, information extraction, alignments, missing text repair.

show abstract

Section: Process Models Have Beenmentioning

confidence: 99%

Missing Procedural Texts Repairing Based on Process Model and Activity Description Templates

Zeng

Tang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent years, scholars in the field of microbiology and molecular biosciences have used the LDA model and its improved algorithm to identify scientific research topics and applied it to intelligence analysis based on text data (Qiu and Yu, 2018;Mehari et al, 2019). In addition to using a corpus (Li et al, 2019), topic modeling can also use additional information, such as time stamp and author network (Rosen-Zvi et al, 2010;Xu et al, 2020), as prior variables or observation variables. Other variants are by embedding new potential variables such as emotions, or by adding constraints applicable to a corpus from a specific scenario (Wang et al, 2018).…”

Section: Topic Modelingmentioning

confidence: 99%

Prediction Correction Topic Evolution Research for Metabolic Pathways of the Gut Microbiota

Peng

Huang

2020

Front. Mol. Biosci.

View full text Add to dashboard Cite

The gut microbiota is composed of a large number of different bacteria, that play a key role in the construction of a metabolic signaling network. Deepening the link between metabolic pathways of the gut microbiota and human health, it seems increasingly essential to evolutionarily define the principal technologies applied in the field and their future trends. We use a topic analysis tool, Latent Dirichlet Allocation, to extract themes as a probabilistic distribution of latent topics from literature dataset. We also use the Prophet neural network prediction tool to predict future trend of this area of study. A total of 1,271 abstracts (from 2006 to 2020) were retrieved from MEDLINE with the query on “gut microbiota” and “metabolic pathway.” Our study found 10 topics covering current research types: dietary health, inflammation and liver cancer, fatty and diabetes, microbiota community, hepatic metabolism, metabolomics-based approach and SFCAs, allergic and immune disorders, gut dysbiosis, obesity, brain reaction, and cardiovascular disease. The analysis indicates that, with the rapid development of gut microbiota research, the metabolomics-based approach and SCFAs (topic 6) and dietary health (topic 1) have more studies being reported in the last 15 years. We also conclude from the data that, three other topics could be heavily focused in the future: metabolomics-based approach and SCFAs (topic 6), obesity (topic 8) and brain reaction and cardiovascular disease (topic 10), to unravel microbial affecting human health.

show abstract

“…A lot of papers work with the comparison between LSA and LDA but it is still not clear which is the winner [23] and it basically depends on cases and corpora. WordNet is applied to LDA to improve the performance when it allows us to differentiate word senses and inherit hypernym and hyponyms hierarchy information to broaden the co-occurrence of terms in documents [24,25]. Many recent methods based on word vectors (Word2Vec, GloVe) generally outperform traditional ones (LSA, PLSA) because they can capture the relatedness of words in topics beside word frequency distribution [11,26].…”

Section: Literature Reviewsmentioning

confidence: 99%

Mining Hidden Topics from Newspaper Quotations: The COVID-19 Pandemic

Rahman

Sidorov

et al. 2020

Advances in Computational Intelligence

View full text Add to dashboard Cite

In this paper, we extract quotations from Al Jazeera's news articles containing keywords related to the COVID-19 pandemic. We apply Latent Dirichlet allocation (LDA), coherence measures, and clustering algorithms to unsupervisedly explore latent topics from the dataset of about 3400 quotations to see how coronavirus impacts human beings. By combining noun phrases as inputs before the training and C v measure for coherence values, we obtain an average coherence value of 0.66 with a least average number of topics of 24.8. The result covers some of the top issues that our world has been facing against the COVID-19 pandemic.

show abstract

Mining Dynamics of Research Topics Based on the Combined LDA and WordNet

Cited by 18 publications

References 22 publications

Missing Procedural Texts Repairing Based on Process Model and Activity Description Templates

Missing Procedural Texts Repairing Based on Process Model and Activity Description Templates

Prediction Correction Topic Evolution Research for Metabolic Pathways of the Gut Microbiota

Mining Hidden Topics from Newspaper Quotations: The COVID-19 Pandemic

Contact Info

Product

Resources

About